diff --git a/models/readme.md b/models/readme.md
index ffc8c37..5f414cb 100644
--- a/models/readme.md
+++ b/models/readme.md
@@ -4,8 +4,10 @@ We have following sets of model files:
 - `json-export-from-repo` - we took models from `xml-repo` and `json-repo`, uploaded them to the [tool](https://biomodelanalyzer.org/tool.html), and exported them (so that we have the newest supported format)
 - `json-export-from-tool` - selection of all models shown in the [tool](https://biomodelanalyzer.org/tool.html), exported in the newest JSON
 
-Note that models can (by design) be replicated in different folders. 
-We just use them to cover wide range of possible formats and model variants, so that we can properly test the parser.
-In future, we should curate them a bit.
+For now, we have collected as many models as possible (from various sources) to cover a wide range of formats and variants, so that we can properly test the parser. 
+We are doing this partially because the internal structure of the models is not always the same. 
+For example, the general structures and field names in XML and JSON formats differ. 
+Also, JSON models in `json-repo` sometimes use a different JSON structure than the ones the tool currently exports.
 
-Note that model formats might not be the same. For example, the XML and JSON formats differ. Also, JSON models in `json-repo` sometimes differ in specific format.
\ No newline at end of file
+Note that this means that (by design) models can be replicated in different folders. 
+In future, we should curate this repository a bit.